Software by Scott Howard Swain

AV Cleaner

Open source, get it here: https://github.com/ScotterMonk/AV-Cleaner

Automates “cleaning” of synchronized dual-video recordings (host + guest) while keeping host/guest perfectly aligned.

Features:

Removes filler words: Detects configured filler words from config.py and mutes them during processing. Depending on length of silence (including surrounding silence), the muted area may be cut in the Cuts pauses step.
Normalizes guest loudness to match the host (or to a standard LUFS target).
Reduces volume spikes in the guest track above a configured threshold.
Cuts pauses: Shortens long mutual-silence pauses to a configurable minimum duration by removing the excess.
Maintains sync by applying the same keep/remove decisions to both videos.

Built in Python with Flask, FFMPEG, and few other dependencies.

AgentAutoFlow

Open source, get it here: https://github.com/ScotterMonk/AgentAutoFlow

Your customizable AI coding team that learns! Use it to create apps or make changes/additions to existing ones.

This set of instructions (markdown files) enhances and extends the modes/agents that come with many coding agents/assistants/scaffolds. The instructions are tailored to work with Kilo Code (free highly customizable VS Code extension) but – with small modifications – will work with many others, including Cursor, CLine, Roo Code, Github Copilot, etc.

Using the built-in-to-Kilo ability to use “rules” files, this archive is a set of custom instructions for the built-in modes/agents and some new ones, including:

Architect Super Team: a 3-step “Planner” process (planner-a, planner-b, planner-c). Brainstorms with user. While planning and working, creates detailed files to keep track of its goals, progress, and lessons learned.
Architect Quick: a 1-step “Planner” process; modified Kilo’s built-in Architect mode to be more detailed but for smaller tasks than full on 3-step “Planner” process.
Dispatcher: I’ve moved much more of the detail work (like making atomic tasks) out of the old/default Orchestrator and into the planning phase so that Dispatcher can be relatively dumb/cheap and merely follow orders to send out detailed tasks to whatever modes are part of each task description.
Coder-Sr: Juiced up Code mode to follow The Plan, whether created by the new superpowered Architect or hastily typed out by a user running 3 days on caffeine.
Coder-Jr: Supplemented Coder-Sr with a tightly controlled budget-friendly Junior Coder created to work with the short, detailed tasks created for it by Planner or Architect or do simple coding tasks for the user.
Other modes added: Added GitHubber, Tasky, Docs Writer, Researcher, etc.

Notes:

Smart and cheap: Designed both Architect and Planner modes to “front load” spend on high “intelligence” thinking models to create a plan that is so detailed, the “Workers” like Dispatcher, Coder-Sr, Coder-Jr, etc. can be faster/cheaper models. Overall, I’m finding this method burns far less tokens, has far less errors, and runs longer without a need for human intervention.
Look how fast they grow up: This set of instructions is ever-evolving.
Virtuous circle: The author, Scott Howard Swain, uses this “Team” every day, is constantly tinkering with it, and is always eager to hear ideas to improve it.
Every time you see .kilocode below, that means the folder containing rules and skills for whatever scaffold you are using.
- For example, it may be “.kilocode” or “.roo”.
Every time you see Kilo Code below, that means the name of the scaffold you are using.
- For example, it may be “Kilo Code” or “Roo Code” or “CLine” or one of the others supported by AgentAutoFlow.

Creative Robot

Promotes your brand using AI analysis of real-time trends guided by human creativity.

Our ai agents collaborate to write blog posts/articles targeting your audience and then they are auto-posted to your web site blog and the social media sites you prefer (as you). Click the image below for more info. Contact Scott to get a free demo.

What is an AI Integrator?

Your Custom Chat Bot

Uses GPT-4 API and trained on your data, which can be documents and/or web pages/sites. We can also give him/her/it a personality. Integrated with your web site to serve your customers.

machine learning natural language model gpt-4 chat bot

Web Browser-based Inventory Management System

Built with Python and Postgres. Responsive: Adapts to browser, tablet, and phone screen sizes.

Inventory Management with Python by Scott Swain

App to mine blockchain data

Built with Python and Beem. Mine’s data from the Hive blockchain, pulling from an API, to tally rewards .

Delivery Logistics

Full featured, browser-based delivery logistics application that tracks brokers, drivers, loads, items-in-loads, and much more.

Empath

Learning and growing since 2018. Chat for free with her now. Share your woes and she will give you empathy!

Empath is a multi-agent NLP ML/AI “Conversational therapist/personal coach/VA”.

2018-current: Designed, coded, trained https://EmpathyBot.net, a natural language processing model initially using a home-brewed pattern-recognition system, pre-LLMs. Built interface for users to easily assist in training the model by critiquing its responses via multi-choice dropdowns for each part of the ML’s response. Next, created an API in Python/Flask to integrate NLTK to increase sentiment accuracy. Added Telegram bot. Added multi-model auto-switching between Claude 3 Opus, 3.5 Sonnet, and GPT-4o APIs, as needed. Four-agent prompt-chain functionality:
(a) “Compressor” reduces size of longer user queries to decrease cost.
(b) “Abuse Detector” determines how far user query is from bot’s intended knowledge domain and acts accordingly, which can include banning a user’s IP address.
(c) “Coach” processes user input and writes a draft response.
(d) “Editor” analyzes potential output for accuracy and kicks it back to “Coach” if needed.
(e) Incorporated Retrieval-Augmented Generation (RAG).

Holopods Project Manager

Hotkey CMS

Full featured CMS I created in 1996 before WordPress was a dream. Includes API calls for live price and time data for UPS, USPS, FedEx, and UPS. Also includes API calls to PayPal and Authorize.net.

Relationships in the HotKey SQL database:

Python game: Zombie Feeder

Game, Source code, and entertaining video.

Python: Cellular automata simulation

Scott Swain created this simulation in alpha-beta behaviors in fish with Python. Frameworks used include Flask, Psycopg2, and Arcade for graphics. Below is a short video of the code in action with sound. Used Visual Studio Code as the IDE.